Similarity Learning with Top-heavy Ranking Loss for Person Re-identification.
Saved in:
| Title: | Similarity Learning with Top-heavy Ranking Loss for Person Re-identification. |
|---|---|
| Authors: | Wang, Jin1, Sang, Nong1, Gao, Changxin1, Wang, Zheng2 |
| Source: | IEEE Signal Processing Letters. Jan2016, Vol. 23 Issue 1, p84-88. 5p. |
| Subjects: | Structural learning theory, Constraints (Physics), Ranking (Statistics), Learning, Video surveillance |
| Abstract: | Person re-identification is the task of finding a person of interest across a network of cameras. In this paper, we propose a new similarity learning method for person re-identification. Conventional metric learning methods generally learn a linear transformation by employing sparse pairwise or triplet constraints. Since a lot of negative matching pairs or triplets are abandoned, the discriminative information is not fully exploited. Similarity learning methods with AUC loss can utilize all valid triplet constraints. However, the AUC loss has its own limitation by treating all false ranks occured at different positions equally. To address this limitation, we propose to extend the AUC loss to the top-heavy ranking loss by assigning large weights to top positions of the ranking list. Moreover, we introduce an explicit nonlinear transformation function for the original feature space and learn an inner product similarity under the structured output learning framework. Our approach achieves very promising results on the challenging VIPeR, CUHK Campus and PRID 450S datasets. [ABSTRACT FROM PUBLISHER] |
| Copyright of IEEE Signal Processing Letters is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 112537979 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Similarity Learning with Top-heavy Ranking Loss for Person Re-identification. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wang%2C+Jin%22">Wang, Jin</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Sang%2C+Nong%22">Sang, Nong</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Gao%2C+Changxin%22">Gao, Changxin</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Wang%2C+Zheng%22">Wang, Zheng</searchLink><relatesTo>2</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Signal+Processing+Letters%22">IEEE Signal Processing Letters</searchLink>. Jan2016, Vol. 23 Issue 1, p84-88. 5p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Structural+learning+theory%22">Structural learning theory</searchLink><br /><searchLink fieldCode="DE" term="%22Constraints+%28Physics%29%22">Constraints (Physics)</searchLink><br /><searchLink fieldCode="DE" term="%22Ranking+%28Statistics%29%22">Ranking (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Learning%22">Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Video+surveillance%22">Video surveillance</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Person re-identification is the task of finding a person of interest across a network of cameras. In this paper, we propose a new similarity learning method for person re-identification. Conventional metric learning methods generally learn a linear transformation by employing sparse pairwise or triplet constraints. Since a lot of negative matching pairs or triplets are abandoned, the discriminative information is not fully exploited. Similarity learning methods with AUC loss can utilize all valid triplet constraints. However, the AUC loss has its own limitation by treating all false ranks occured at different positions equally. To address this limitation, we propose to extend the AUC loss to the top-heavy ranking loss by assigning large weights to top positions of the ranking list. Moreover, we introduce an explicit nonlinear transformation function for the original feature space and learn an inner product similarity under the structured output learning framework. Our approach achieves very promising results on the challenging VIPeR, CUHK Campus and PRID 450S datasets. [ABSTRACT FROM PUBLISHER] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Signal Processing Letters is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=112537979 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/LSP.2015.2502271 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 5 StartPage: 84 Subjects: – SubjectFull: Structural learning theory Type: general – SubjectFull: Constraints (Physics) Type: general – SubjectFull: Ranking (Statistics) Type: general – SubjectFull: Learning Type: general – SubjectFull: Video surveillance Type: general Titles: – TitleFull: Similarity Learning with Top-heavy Ranking Loss for Person Re-identification. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wang, Jin – PersonEntity: Name: NameFull: Sang, Nong – PersonEntity: Name: NameFull: Gao, Changxin – PersonEntity: Name: NameFull: Wang, Zheng IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Text: Jan2016 Type: published Y: 2016 Identifiers: – Type: issn-print Value: 10709908 Numbering: – Type: volume Value: 23 – Type: issue Value: 1 Titles: – TitleFull: IEEE Signal Processing Letters Type: main |
| ResultId | 1 |
